University of Southern California, Los Angeles, USA.
University of California San Francisco, San Francisco, USA.
Sci Rep. 2021 Jun 3;11(1):11730. doi: 10.1038/s41598-021-90000-4.
Machine learning (ML) models have demonstrated the power of utilizing clinical instruments to provide tools for domain experts in gaining additional insights toward complex clinical diagnoses. In this context these tools desire two additional properties: interpretability, being able to audit and understand the decision function, and robustness, being able to assign the correct label in spite of missing or noisy inputs. This work formulates diagnostic classification as a decision-making process and utilizes Q-learning to build classifiers that meet the aforementioned desired criteria. As an exemplary task, we simulate the process of differentiating Autism Spectrum Disorder from Attention Deficit-Hyperactivity Disorder in verbal school aged children. This application highlights how reinforcement learning frameworks can be utilized to train more robust classifiers by jointly learning to maximize diagnostic accuracy while minimizing the amount of information required.
机器学习（ML）模型已经证明了利用临床工具为领域专家提供工具的强大功能，以帮助他们更深入地了解复杂的临床诊断。在这种情况下，这些工具需要具备两个额外的特性：可解释性，能够对决策函数进行审核和理解；鲁棒性，即使输入缺失或存在噪声，也能够正确地分配标签。这项工作将诊断分类表述为一个决策过程，并利用 Q 学习来构建满足上述期望标准的分类器。作为一个示例任务，我们模拟了区分言语学龄儿童自闭症谱系障碍和注意力缺陷多动障碍的过程。该应用程序强调了强化学习框架如何通过联合学习来最大化诊断准确性并最小化所需信息量，从而训练更鲁棒的分类器。
